Borrowing it
Nothing to install: this file belongs to SebAustin/mcp-financial-data. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SebAustin/mcp-financial-data/main/AGENTS.mdgit clone --depth 1 https://github.com/SebAustin/mcp-financial-dataWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sebaustin/mcp-financial-data/agents-md)<a href="https://agentmods.dev/instructions/sebaustin/mcp-financial-data/agents-md"><img src="https://agentmods.dev/badge/instructions/sebaustin/mcp-financial-data/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/sebaustin/mcp-financial-data/agents-md"><img src="https://agentmods.dev/badge/instructions/sebaustin/mcp-financial-data/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00458 | $0.00458 |
| Opus 5.5 | $0.00183 | $0.00183 |
| Sonnet 5.5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
mcp-financial-data AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md
Pointer file for any AI agent (Cursor, Claude Code, Codex) opening this repo.
Read these first, in order
.cursorrules— master portfolio rules + project deltas. Non-optional.docs/adr/— every architectural decision is captured here in MADR.evals/harness.py— the source of truth for "is this thing working".
What this repo is
An MCP server (spec 2025-11-25) that exposes SEC EDGAR + FRED + Polygon financial data with OAuth 2.1, plus a Claude-powered 10-K extractor that returns citation-grounded claims, plus an MCP Apps inline UI component.
Anchor audience: Anthropic Forward Deployed Engineering, Bridgewater / Citadel / Anthropic Finance teams.
Hard constraints (skim before generating code)
- Citations: Every claim from the 10-K extractor must carry an Anthropic Citations API reference. Uncited claims are dropped.
- EDGAR Fair Access: Every EDGAR call needs a contact User-Agent and the process is rate-limited to ≤ 10 req/sec.
- Spend cap:
MAX_API_SPEND_USDenv var is enforced in the extractor and the eval harness. CI runs--offline. - OAuth 2.1: This server is the resource server. Validate JWTs against the configured JWKS; never hardcode public keys.
- **No
requests, noprint(), nosubprocess shell=True, no bareexcept.
What "done" looks like for the W1 sprint
make ciexits 0 (lint + typecheck + test ≥85% + smoke eval).- A 60-second Loom demo of: OAuth round-trip → MCP tool call → 10-K extract with visible citation pills → MCP Apps inline UI rendering.
- README.md eval table populated with real numbers from a
--fullrun. - Tag
v0.1.0, three GitHub issues filed for follow-on work, applications to Anthropic FDE + Cursor FDE sent.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 40 lines · 458 tokens per session scan A c0a9642ffc96
mcp-financial-data AGENTS.md is an instructions file published in the GitHub repository SebAustin/mcp-financial-data (0 stars, last pushed 2mo ago), licensed MIT. It adds 458 tokens to every session, about $0.0018 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
mcp-financial-data AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-financial-data AGENTS.mdSebAustin/mcp-financial-data | Instructions file | 0 | 2mo ago | MIT | A | 458 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |